一种区间限定预检测的误配点剔除算法

doi:10.3969/j.issn.1001-2400.2013.05.017

Abstract

Abstract:

The elimination of mismatching point is a key step in image mosaic. To speed up the mismatching point elimination in image matching, an efficient algorithm for mismatching point elimination is presented. Based on the RANSAC(random sample consensus) algorithm, the algorithm aims at the feature of the image sequence. First, the match points are sorted, divided into three parts and piecewise picked randomly to estimate the transforming matrix. Second, the matrix is cursorily checked with a novel interzone limited pre-test model, a further check is executed on the matrix that passes the pre-testing to get inliers. Finally, the least-square method is used to the inliers to get the real matrix. Experimental results suggest that the proposed algorithm is of lower complexity, higher accuracy and stableness especially in cruel conditions, which meets the demand of image sequence mosaic well.

Key words: image matching, mismatching point, random sample consensus algorithm, pre-test, piecewise

WAN Guoting;WANG Junping;CAO Honghua;WANG Song;WANG Le. Efficient algorithm for mismatching point elimination with interzone limited pre-testing[J].J4, 2013, 40(5): 107-112+199.

References

［1］王勃, 龚志辉, 顾广杰. 一种快速的无人机影像无缝拼接方法［J/OL］. ［2011-11-16］. http://www.cnki.net/kcms/detail/11.4415.P.20111116.1025.039.html.
［2］ Yang P, Mao Z, Gao A J, et al. Video Image Mosaics in Real-time Based on SIFT［C］//Proceedings of 2010 First International Conference on Pervasive Computing, Signal Processing and Applications. Los Alamitos: IEEE, 2010: 879-882.
［3］ Reddy B S, Chatterji B N. An FFT-based Technique for Translation, Rotation and Scale-invariant Image Registration［J］. IEEE Transactions on Image Processing, 1996, 8(5): 1266-1271.
［4］ Moritani M, Saitoh F. Image Template Matching Based on Ratio of Mean and Central Pixel in Local Area［DB/OL］. ［2012-03-20］. http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=829671 .
［5］ Zitova B, Flusser J. Image Registration Methods: a Survey［J］. Image and Vision Computing, 2003, 21(11): 977-1000.
［6］刘金根, 吴志鹏, 刘上乾, 等. 一种基于特征区域分割的图像拼接算法［J］. 西安电子科技大学学报, 2002, 29(6): 768-772.
Liu Jingen, Wu Zhipeng, Liu Shangqian, et al. A Merging Algorithm for Images Based on Segmentation of Feature Regions［J］. Journal of Xidian University, 2002, 29(6): 768-772.
［7］陈冰, 赵亦工, 李欣. 一种新的宽基线图像匹配方法［J］. 西安电子科技大学学报, 2011, 38(2): 116-123.
Chen Bing, Zhao Yigong, Li Xin. Wide Baseline Image Matching Based on a New Local Descriptor［J］. Journal of Xidian University, 2011, 38(2): 116-123.
［8］田毅珂, 徐斌, 卢朝阳, 等. 序列图像场景一致性判断［J］. 西安电子科技大学学报, 2002, 29(2): 196-200.
Tian Yike, Xu Bin, Lu Zhaoyang, et al. Scene Identification in Image Sequence［J］. Journal of Xidian University, 2002, 29(2): 196-200.
［9］ Jiang M Q, Liao Q W, Hong J X, et al. A Sift-Based Method for Image Mosaic［C］//Proceedings of 2010 3rd International Conference on Advanced Computer Theory and Engineering. Piscataway: IEEE, 2010: V6423-V6427.
［10］林秉雄. SIFT特征匹配标准与匹配方式的改进与应用［D］. 大连: 大连理工大学, 2010.
［11］ Li J, Wang Y W, Liang H. Image Mosaic based on Simplified SIFT［DB/OL］. ［2012-03-10］. http://www.ier-institute.org/2160-0589/abe10/v101090.pdf.
［12］ Fischler M A, Bolles R C. Random Sample Consensus: a Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography［J］. Communications of the ACM, 1981, 24(6): 381-395.
［13］曲天伟, 安波, 陈桂兰. 改进的RANSAC算法在图像配准中的应用［J］. 计算机应用, 2010, 7(30): 1849-1851.
Qu Tianwei, An Bo, Chen Guilan. Application of Improved RANSAC Algorithm to Image Registration［J］. Journal of Computer Applications, 2010, 7(30): 1849-1851.
［14］ Matas J, Chum O. Randomized RANSAC with T_d,d Test［J］. Image and Vision Computing, 2004, 22(10): 837-842.
［15］ Matas J, Chum O. Randomized RANSAC with Sequential Probability Ratio Test［C］//Tenth IEEE International Conference on Computer Vision. Los Alamitos: IEEE Computer Society, 2005: 1727-1732.
［16］ Chen F X, Wang R S. Fast Ransac with Preview Model Parameters Evaluation［J］. Journal of Software, 2005,16: 1431-1437.
［17］ Sattler T, Leibe B, Kobbelt L. SCRAMSAC: Improving RANSAC's Efficiency with a Spatial Consistency Filter［C］//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE, 2009: 2090-2097.
［18］ Sze W F, Tang W K, Hung Y S. Dynamic RANSAC ［DB/OL］. ［2012-03-15］. http://hub.hku.hk/handle/10722199379.
［19］ Chum O, Matas J. Optimal Randomized RANSAC［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 8(30): 1472-1482.

[1]	NGUYEN Van-Truong,CAI Jueping,WEI Linyu,CHU Jie. Low complexity probability-based piecewise linear approximation of the sigmoid function [J]. Journal of Xidian University, 2020, 47(3): 58-65.
[2]	TANG Guoliang. Anti-fuzzy local feature descriptor on images [J]. Journal of Xidian University, 2019, 46(1): 39-45.
[3]	YANG Siyan;CAO Wencan;LI Shiping. Second-order graph model ant and colony optimization based image matching [J]. Journal of Xidian University, 2017, 44(1): 159-164.
[4]	MA Liwen;GUO Yukun;LI Jinping. Traffic violation detection based on the implicit curves family [J]. Journal of Xidian University, 2016, 43(2): 139-144.
[5]	ZHAO Baowei;XIANGLI Bin;HUANG Min;LV Qunbo;ZHANG Guifeng. Matching method for multispectral images based on improved hough transformation with disparity constraint [J]. J4, 2015, 42(6): 94-98.
[6]	CHEN Bing;ZHAO Yigong;LI Xin. Wide baseline image matching based on a new local descriptor [J]. J4, 2011, 38(2): 116-123.
[7]	CHEN Zhi-hui1;CHU Qing-xin2. Novel FDTD method for modeling arbitrary linear lumped networks [J]. J4, 2008, 35(2): 262-266.
[8]	GUO Da-bo1;2;LU Zhao-yang1;HE Hua-jun1;JIAO Wei-dong1. New algorithm for stereo disparity estimation [J]. J4, 2007, 34(3): 337-341.
[9]	LI Jun-min(1);LI Jiang-rong(2). Piecewise generalized H₂ dynamic output feedback control for discrete-time piecewise systems [J]. J4, 2006, 33(6): 985-989.

Efficient algorithm for mismatching point elimination with interzone limited pre-testing

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 9

Metrics

Comments

Recommended 0